Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    emotional expressions, particularly those involving disbelief or outrage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Punctuation followed by sentence continuation

    np_acts-logits-general · gemini-2.0-flash

    strong emotions and opinions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ślę
    -0.68
     surla
    -0.66
    iyi
    -0.61
     occasional
    -0.60
     occasionally
    -0.56
    =$?
    -0.56
    %"),
    -0.56
     gerne
    -0.55
     Occasionally
    -0.55
    houette
    -0.54
    POSITIVE LOGITS
    Seriously
    0.97
     literally
    0.92
     Seriously
    0.91
     zelfs
    0.89
     even
    0.87
     unbelievable
    0.87
    seriously
    0.86
     Literally
    0.85
     incredible
    0.84
     litté
    0.83
    Act Density 0.227%

    No Known Activations